hyparquet/test/read.test.js

50 lines
1.4 KiB
JavaScript
Raw Normal View History

2024-02-14 05:11:34 +00:00
import fs from 'fs'
2024-01-15 19:08:48 +00:00
import { describe, expect, it } from 'vitest'
import { parquetRead } from '../src/hyparquet.js'
import { toJson } from '../src/toJson.js'
2024-02-14 05:11:34 +00:00
import { fileToAsyncBuffer, fileToJson } from './helpers.js'
2024-01-15 19:08:48 +00:00
describe('parquetRead', () => {
2024-02-27 03:33:38 +00:00
const files = fs.readdirSync('test/files').filter(f => f.endsWith('.parquet'))
2024-02-24 19:01:08 +00:00
files.forEach(file => {
it(`should parse data from ${file}`, async () => {
2024-02-14 05:11:34 +00:00
const asyncBuffer = fileToAsyncBuffer(`test/files/${file}`)
await parquetRead({
file: asyncBuffer,
onComplete: (rows) => {
const base = file.replace('.parquet', '')
const expected = fileToJson(`test/files/${base}.json`)
expect(toJson(rows)).toEqual(expected)
},
})
2024-02-24 19:01:08 +00:00
})
2024-01-15 19:08:48 +00:00
})
2024-02-27 03:33:38 +00:00
it('should read a single column from a file', async () => {
const asyncBuffer = fileToAsyncBuffer('test/files/datapage_v2.snappy.parquet')
await parquetRead({
file: asyncBuffer,
columns: [2],
onChunk: (rows) => {
expect(toJson(rows)).toEqual({
column: 2,
data: [2, 3, 4, 5, 2],
rowStart: 0,
rowEnd: 5,
})
},
onComplete: (rows) => {
/* eslint-disable no-sparse-arrays */
expect(toJson(rows)).toEqual([
[,, 2],
[,, 3],
[,, 4],
[,, 5],
[,, 2],
])
},
})
})
2024-01-15 19:08:48 +00:00
})